Research map / Graph learning / GNN architectures
Revisiting Graph Based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| combine linear embedding propagation with residual preference prediction | LR-GCCF · Amazon Books | HR@20: 0.03244 -> 0.03407 | Helped |
| combine linear embedding propagation with residual preference prediction | LR-GCCF · Gowalla | HR@20: 0.1403 -> 0.1518 | Helped |
| replace nonlinear transformations with linear embedding propagation (ablation) | GC-MC · Amazon Books | HR@20: 0.03196 -> 0.03248 | Helped |
| replace nonlinear transformations with linear embedding propagation (ablation) | GC-MC · Gowalla | HR@20: 0.1388 -> 0.1399 | Helped |
| add residual preference learning (ablation) | linear GCCF · Amazon Books | HR@20: 0.03200 -> 0.03407 | Helped |
| add residual preference learning (ablation) | linear GCCF · Gowalla | HR@20: 0.1412 -> 0.1518 | Helped |
| add residual preference prediction (ablation) | GC-MC · Amazon Books | HR@20: 0.03196 -> 0.03084 | Hurt |
| increase propagation depth from K=0 to K=1 (ablation) | LR-GCCF · Amazon Books | HR@20: 0.0285 -> 0.0317 | Helped |
| increase propagation depth from K=0 to K=1 (ablation) | LR-GCCF · Gowalla | HR@20: 0.1378 -> 0.1504 | Helped |
| increase propagation depth beyond K=3 (ablation) | LR-GCCF · Gowalla | HR@20: 0.1518 -> 0.1494 | Hurt |
Closest papers by meaning
- Multi-Component Graph Convolutional Collaborative Filtering (AAAI 2020 · similarity 0.93)
- Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering (ICML 2025 · similarity 0.91)
- Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs (AAAI 2025 · similarity 0.90)
- TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation (NeurIPS 2025 · similarity 0.89)
- Semantic Enhanced Heterogeneous Hypergraph Network for Collaborative Filtering (AAAI 2025 · similarity 0.88)
- LGMRec: Local and Global Graph Learning for Multimodal Recommendation (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.